CN104438350B - Strip steel mechanical performance online detection and control method in leveling process - Google Patents
Strip steel mechanical performance online detection and control method in leveling process Download PDFInfo
- Publication number
- CN104438350B CN104438350B CN201310436580.4A CN201310436580A CN104438350B CN 104438350 B CN104438350 B CN 104438350B CN 201310436580 A CN201310436580 A CN 201310436580A CN 104438350 B CN104438350 B CN 104438350B
- Authority
- CN
- China
- Prior art keywords
- strip steel
- smooth
- mechanical performance
- elongation percentage
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Control Of Metal Rolling (AREA)
Abstract
The invention relates to the field of plate and strip rolling, in particular to a plate and strip leveling quality control method. According to a strip steel mechanical performance online detection and control method in the leveling process, firstly, a model input quantity and a model output quantity are selected and used, and a three-layer BP neural network model of the corresponding relation between leveling process relative parameters and strip steel mechanical performance is built; according to strip steel of a specific steel type, measured values of n groups of the leveling process relative parameters and measured values of strip steel mechanical performance parameters are collected and recorded to serve as training samples of the neural network model, learning and training are performed on a neural network by means of the BP method, and in other words, a mechanical performance forecast model of the strip steel of the steel type is obtained; by means of the mechanical performance forecast model, online control of strip steel mechanical performance in the leveling process is achieved. The leveling process parameters are adjusted according to the judgment result of a mechanical performance forecast value, online control of the strip steel mechanical performance parameters is achieved, and accordingly a strip steel material small in yield ratio can be obtained, and good forming performance of the strip steel is kept.
Description
Technical field
The present invention relates to board rolling field, the smooth method of quality control of more particularly, to a kind of strip.
Background technology
In the practice of current cold rolled strip steel production, to the usual mode that strip steel mechanical performance is monitored it is, related
Cold rolling post processing machine set outlet, carries out sampling observation sampling to strip steel, then carries out off-line test in analysis test laboratory to model
Obtain the mechanical performance parameter of strip steel, and be compared with the technical requirements of downstream user.If strip steel mechanical performance is unsatisfactory for
The requirement of downstream user, then in follow-up production, the processing parameter to similar strip steel or material alloys elementary composition etc. enter
Row necessary adjustment.Then sampling, off-line analysiss test, on-line tuning fabrication process parameters or material composition etc. are inspected again by random samples, until
Till the mechanical performance of strip steel fully meets downstream user requirement.The mechanical performance parameter that this offline inspection is obtained is merely able to
Limitedly it is used for Instructing manufacture technique adjustment or material composition adjustment, and there is longer time hysteresis quality.Simultaneously because taking out
Search sample and offline inspection has noncontinuity it is impossible to obtain strip property parameter just in process of production online, and
Generally the head of coiled strip steel or tail can only be sampled with detection it is difficult to ensure that strip steel is each on entire volume length direction
The mechanical performance index at place is all within the scope of user requires.
In order to obtain the cold-rolling galvanization strip steel of few fault in material, Japan Patent jp09118926a proposes a kind of hot rolled plate
The whether thick detection of volume crystal grain and processing method, adopt contactless magnetic head on-line checking hot-rolled sheet coil after pickling
Barkhausen noise magnitude of voltage, judges whether take the lead magnetic tape trailer material grains thick accordingly.If take the lead or magnetic tape trailer to there is crystal grain thick
Big part, then enter cold rolling and annealing before by have fault in material take the lead or magnetic tape trailer part strip steel cuts away.
In recent years, with the fast development of detection technique, the mechanical performance of on-line checking cold-strip steel is possibly realized.Respectively
State all is being devoted to solving lossless online measuring technique.
Content of the invention
The technical problem to be solved is to provide a kind of formation process strip steel mechanical performance online detection and control side
Method, the method can indirectly obtain the mechanical performance parameter predicted value of this steel grade specification strip steel using flattening process relevant parameter, and
The result of determination being worth according to weather report is adjusted to flattening process relevant parameter, realizes to strip steel mechanical performance parameter in line traffic control
System, to obtain belt steel material less Qu Qiang ratio, thus keep the good processability of strip steel.
The present invention is achieved in that a kind of formation process strip steel mechanical performance online detection and control method, including following
Step:
Step one, select flattening process relevant parameter first as mode input amount, using strip steel mechanical performance parameter as
Model output, sets up three layers of bp neural network model of corresponding relation between flattening technological parameter and strip steel mechanical performance;
Step 2, a certain select location being directed on a certain steel grade specification strip steel length direction, collect and record putting down at this
The measured value of whole technique relevant parameter, when the strip steel after smooth enters unit sampling section, is sampled to strip steel at this, leads to
Cross destruction method of testing offline to carry out testing the measured value obtaining strip steel mechanical performance parameter;
Step 3, step 2 is repeated several times, obtains n group flattening process relevant parameter and the strip steel machine of this steel grade specification strip steel
Tool performance parameter;
Step 4, the n group data that step 3 is obtained as the training sample of neural network model, using bp method to god
Carry out learning training through network, that is, obtain the mechanical performance forecasting model of this steel grade specification strip steel;
Step 5, by the mechanical performance forecasting model good through learning training embed planisher automatic control system, input
The measured value of flattening process relevant parameter realizes the forecast to strip steel mechanical performance parameter, to obtained strip steel mechanical performance ginseng
Number predicted value is judged, according to result of determination, smooth elongation percentage is adjusted correspondingly, and realizes to formation process strip steel machine
The On-line Control of tool performance.
In described step one, the parameter as mode input amount has 11, respectively steel grade charcoal equivalent cd, annealing temperature
te, unit width skin pass rolling power p, smooth entrance tensile stress σ0, smooth outlet answer tension force σ1, smooth speed v, work roll diameter
dw, leveling precision concentration c, belt steel thickness h, leveling roll rolling milimeter number l, smooth elongation percentage actual value ε;As model output
Parameter has two, respectively yield strength σs, tensile strength sigmab;Set up mode input amount and model output corresponding relation
The intermediate layer of 19 units, i.e. 11 lists of input layer in three layers of bp neural network model are set during three layers of bp neural network model
Unit, 19, intermediate layer unit, 2 units of output layer.
In described step 5, smooth elongation percentage is adjusted, when strip steel is that belt steel thickness is less than or equal to for Thin Strip Steel
During 0.3mm, if yield strength predicted value exceedes the yield strength desired value upper limit, reduce smooth entrance tensile stress by preferential
σ0, smooth outlet answer tension force σ1To reduce smooth elongation percentage, to work as σ0、σ1Pass through again during super lower limit to reduce unit width skin pass rolling
Power p is reducing smooth elongation percentage;If tensile strength prediction value is less than tensile strength desired value lower limit, put down by preferential increase
Whole entrance tensile stress σ0, smooth outlet answer tension force σ1To increase smooth elongation percentage, to work as σ0、σ1Pass through again during the super upper limit to increase unit
Width skin pass rolling power p is increasing smooth elongation percentage.
In described step 5, smooth elongation percentage is adjusted, when strip steel for Deformation in thick be belt steel thickness be more than 0.3mm
When, if yield strength predicted value exceedes the yield strength desired value upper limit, reduce unit width skin pass rolling power p by preferential
To reduce smooth elongation percentage, when the super lower limit of p passes through to reduce smooth entrance tensile stress σ again0, smooth outlet answer tension force σ1Flat to reduce
Whole elongation percentage;If tensile strength prediction value is less than tensile strength desired value lower limit, smooth by preferential increase unit width
Roll-force p increasing smooth elongation percentage, when the super upper limit of p is passed through to increase smooth entrance tensile stress σ again0, smooth outlet answer tension force σ1Come
Increase smooth elongation percentage.
Also include before described step 4 obtained n group flattening process relevant parameter and strip steel mechanical performance parameter are entered
The step of row reasonableness check.
Formation process strip steel mechanical performance online detection and control method of the present invention utilizes in advance known or passes through online
The flattening process relevant parameter that real-time monitoring obtains, as mode input amount, obtains corresponding strip steel machine by sampling off-line test
Tool performance parameter, as model output, adopts bp method to nerve after the data that have accumulated sufficient amount a certain steel grade specification
Network carries out learning training, indirectly obtains the mechanical performance parameter predicted value of this steel grade specification strip steel, makes planisher play strip steel
The effect of mechanical performance sensor, and the result of determination being worth according to weather report is adjusted to flattening process relevant parameter, it is right to realize
The On-line Control of strip steel mechanical performance parameter;The fluctuation of strip steel mechanical performance can be reduced to a certain extent, it is to avoid surrender occurs strong
Situations such as degree higher, low cross-intensity, to obtain belt steel material less Qu Qiang ratio, thus keep the good mouldability of strip steel
Energy;This method can be widely applied to each cold rolled sheet continuous galvanizing line large number of both at home and abroad, continuous annealing unit with
And skin pass mill group, popularizing application prospect is wide.
Brief description
Fig. 1 is three layers of bp neural network model in formation process strip steel mechanical performance online detection and control method of the present invention
Figure;
Fig. 2 is neural network model yield strength training error scatterplot in embodiment;
Fig. 3 is neural network model tensile strength training error scatterplot in embodiment.
Specific embodiment
With reference to specific embodiment, the present invention is expanded on further.It should be understood that these embodiments are merely to illustrate the present invention
Rather than restriction the scope of the present invention.In addition, it is to be understood that after having read the content of present invention statement, people in the art
Member can make various changes or modifications to the present invention, and these equivalent form of values equally fall within the application appended claims and limited
Scope.
Embodiment 1
A kind of formation process strip steel mechanical performance online detection and control method, comprises the following steps:
Step one, select flattening process relevant parameter first as mode input amount, using strip steel mechanical performance parameter as
Model output, sets up three layers of bp neutral net mould of corresponding relation between flattening process relevant parameter and strip steel mechanical performance
Type;Parameter as mode input amount has 11 in the present embodiment, respectively steel grade charcoal equivalent cd, annealing temperature te, unit
Width skin pass rolling power p, smooth entrance tensile stress σ0, smooth outlet answer tension force σ1, smooth speed v, work roll diameter dw, smooth
Liquid concentration c, belt steel thickness h, leveling roll rolling milimeter number l, smooth elongation percentage actual value ε;Parameter as model output is common
There are two, respectively yield strength σs, tensile strength sigmab;Set up three layers of bp of mode input amount and model output corresponding relation
The intermediate layer of 19 units, i.e. 11 units of input layer in three layers of bp neural network model, centre are set during neural network model
19 unit of layer, 2 units of output layer;
Step 2, a certain select location being directed on a certain steel grade specification strip steel length direction, collect and record putting down at this
The measured value of whole technique relevant parameter, when the strip steel after smooth enters unit sampling section, is sampled to strip steel at this, leads to
Cross destruction method of testing offline to carry out testing the measured value obtaining strip steel mechanical performance parameter;
Step 3, step 2 is repeated several times, obtains n group flattening process relevant parameter and the strip steel machine of this steel grade specification strip steel
Tool performance parameter,
;
In formula, i- parameter group sequence number,
σsi- the i-th group yield strength,
σbi- the i-th group tensile strength,
εi- the i-th group smooth elongation percentage actual value,
pi- unit width skin pass rolling power,
σ0i- the i-th group smooth entrance tensile stress,
σ1i- the i-th group smooth outlet tensile stress,
viThe smooth speed of-the i-th group,
dwi- the i-th group work roll diameter,
cdi- the i-th group charcoal equivalent,
tei- the i-th group annealing temperature,
ci- the i-th group leveling precision concentration,
li- the i-th group leveling roll rolling milimeter number,
hi- the i-th unit strip steel thickness;
Step 4, the wrong data in order to avoid some mutation have influence on last forecast result, first to obtained n
Group flattening process relevant parameter and strip steel mechanical performance parameter carry out reasonableness check, use " 3 σ principle ", that is, will be far from parameter
Average is determined as outlier more than the value of 3 standard deviation sigma.Peel off differentiation to each parameter of every group of data, if one group of number
According to certain parameter be outlier, then by this group data dump, the n group data then obtaining step 3 is as neutral net
The training sample of model, carries out learning training using bp method to neutral net, that is, obtain the mechanicalness of this steel grade specification strip steel
Energy forecasting model,
;
Step 5, by the mechanical performance forecasting model good through learning training embed planisher automatic control system, smooth
The measured value of technique relevant parameter realizes the forecast to strip steel mechanical performance parameter, pre- to obtained strip steel mechanical performance parameter
Report value is judged, according to result of determination, smooth elongation percentage is adjusted correspondingly, and realizes to formation process strip steel mechanicalness
The On-line Control of energy.
In the present embodiment, when smooth elongation percentage being adjusted, strip steel is divided into Thin Strip Steel and Deformation in thick two class,
The thickness of wherein Thin Strip Steel is less than or equal to 0.3mm, and the thickness of Deformation in thick is more than 0.3mm.
When strip steel is for Thin Strip Steel, if yield strength predicted value exceedes the yield strength desired value upper limit, by preferential
Reduce smooth entrance tensile stress σ0, smooth outlet answer tension force σ1To reduce smooth elongation percentage, to work as σ0、σ1Pass through again during super lower limit to subtract
Subsection width skin pass rolling power p is reducing smooth elongation percentage;If tensile strength prediction value is less than under tensile strength desired value
In limited time, then pass through the smooth entrance tensile stress σ of preferential increase0, smooth outlet answer tension force σ1To increase smooth elongation percentage, to work as σ0、σ1Super
Increase smooth elongation percentage by increasing unit width skin pass rolling power p again during the upper limit.
When strip steel is for Deformation in thick, if yield strength predicted value exceedes the yield strength desired value upper limit, by preferential
Reduce unit width skin pass rolling power p to reduce smooth elongation percentage, when the super lower limit of p passes through to reduce smooth entrance tensile stress σ again0、
Tension force σ is answered in smooth outlet1To reduce smooth elongation percentage;If tensile strength prediction value is less than tensile strength desired value lower limit,
Then smooth elongation percentage is increased by preferential unit width skin pass rolling power p that increases, when the super upper limit of p is passed through to increase smooth entrance again
Tensile stress σ0, smooth outlet answer tension force σ1To increase smooth elongation percentage.
With this to avoid to a certain extent strip steel yield strength is higher, low cross-intensity, to obtain this steel grade rule
Lattice strip steel less Qu Qiang ratio, thus keep the good processability of strip steel.
The actual flattening process of 06cr19ni10 coiled sheet of certain skin pass mill group production is have collected altogether in the step 3 of the present embodiment
Relevant parameter and totally 289 groups of corresponding actual measurement mechanical performance parameter, as training sample, instruct to bp neural network model
Practice, as shown in Figure 2 and Figure 3,289 groups of sample errors, all within 1%, illustrate that model training result is reliable to model training error
's.
Model prediction precision is verified.Collect the actual flattening process relevant parameter of other 10 groups of 06cr19ni10 strip steel and right
The actual measurement mechanical performance parameter answered is as the test sample of inspection model prediction precision after training, actual flat by 10 groups
Whole technique relevant parameter is brought in the mechanical performance forecasting model of strip steel and is forecast, obtains the forecast of strip steel mechanical performance parameter
Value result is as shown in table 1,
The relative forecast precision of model is higher from the results shown in Table 1, in addition to the 7th group all within 20%, machine
The precision of tool performance predictive model substantially meets requirement.
In order to check the actual effect of above-mentioned strip steel mechanical performance Detection & Controling model, before the technology is implemented,
After enforcement, have collected certain skin pass mill group respectively and produce certain more each 21 groups of steel grade corrosion resistant plate actual machine performance data,
In two groups of data, yield strength maximum, tensile strength minima and yield tensile ratio meansigma methodss are as shown in table 2.
Table 2 mechanical performance Control experiment result
As can be seen that after enforcement the technology, the actual Qu Qiang of strip steel reduces than, and yield strength maximum has subtracted
Little, tensile strength has increased.
Claims (2)
1. a kind of formation process strip steel mechanical performance online detection and control method, is characterized in that, comprise the following steps:
Step one, first select flattening process relevant parameter as mode input amount, using strip steel mechanical performance parameter as model
Output, sets up three layers of bp neural network model of corresponding relation between flattening process relevant parameter and strip steel mechanical performance;
Parameter as mode input amount has 11, respectively steel grade charcoal equivalent cd, annealing temperature te, unit width leveling rolling
Power p processed, smooth entrance tensile stress σ0, smooth outlet tensile stress σ1, smooth speed v, work roll diameter dw, leveling precision concentration c, band
Steel thickness h, leveling roll rolling milimeter number l, smooth elongation percentage actual value ε;Parameter as model output has two, respectively
For strip steel yield strength σs, tensile strength sigmab;Set up three layers of bp neutral net of mode input amount and model output corresponding relation
The intermediate layer of 19 units, i.e. 11 units of input layer in three layers of bp neural network model, 19, intermediate layer list are set during model
Unit, 2 units of output layer;
Step 2, a certain select location being directed on a certain steel grade specification strip steel length direction, collect the smooth work recording at this
The measured value of skill relevant parameter, when strip steel after smooth enters unit sampling section, is sampled to strip steel at this, by from
Line destroys method of testing to carry out testing the measured value obtaining strip steel mechanical performance parameter;
Step 3, step 2 is repeated several times, obtains n group flattening process relevant parameter and the strip steel mechanicalness of this steel grade specification strip steel
Can parameter;
Step 4, the n group data that step 3 is obtained as the training sample of neural network model, using bp method to nerve net
Network carries out learning training, that is, obtain the mechanical performance forecasting model of this steel grade specification strip steel;
Step 5, by the mechanical performance forecasting model good through learning training embed planisher automatic control system, input smooth
The measured value of technique relevant parameter realizes the forecast to strip steel mechanical performance parameter, pre- to obtained strip steel mechanical performance parameter
Report value is judged, according to result of determination, smooth elongation percentage is adjusted correspondingly, and realizes to formation process strip steel mechanicalness
The On-line Control of energy;
In described step 5, smooth elongation percentage is adjusted, when strip steel is that belt steel thickness is less than or equal to 0.3mm for Thin Strip Steel
When, if yield strength predicted value exceedes the yield strength desired value upper limit, reduce smooth entrance tensile stress σ by preferential0, flat
Whole outlet tensile stress σ1To reduce smooth elongation percentage, to work as σ0、σ1During super lower limit again by reduce unit width skin pass rolling power p Lai
Reduce smooth elongation percentage;If tensile strength prediction value is less than tensile strength desired value lower limit, by preferential increase smooth enter
Mouth tensile stress σ0, smooth outlet tensile stress σ1To increase smooth elongation percentage, to work as σ0、σ1Pass through again during the super upper limit to increase unit width
Skin pass rolling power p is increasing smooth elongation percentage;
In described step 5, smooth elongation percentage is adjusted, when strip steel is that belt steel thickness is more than 0.3mm for Deformation in thick, if
Yield strength predicted value exceedes the yield strength desired value upper limit, then reduced by preferential unit width skin pass rolling power p that reduces
Smooth elongation percentage, when the super lower limit of p passes through to reduce smooth entrance tensile stress σ again0, smooth outlet answer tension force σ1To reduce smooth extension
Rate;If tensile strength prediction value is less than tensile strength desired value lower limit, increase unit width skin pass rolling power p by preferential
To increase smooth elongation percentage, when the super upper limit of p is passed through to increase smooth entrance tensile stress σ again0, smooth outlet answer tension force σ1Flat to increase
Whole elongation percentage.
2. formation process strip steel mechanical performance online detection and control method as claimed in claim 1, is characterized in that: described step
Also included obtained n group flattening process relevant parameter and strip steel mechanical performance parameter are carried out with the step of reasonableness check before four
Suddenly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310436580.4A CN104438350B (en) | 2013-09-24 | 2013-09-24 | Strip steel mechanical performance online detection and control method in leveling process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310436580.4A CN104438350B (en) | 2013-09-24 | 2013-09-24 | Strip steel mechanical performance online detection and control method in leveling process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104438350A CN104438350A (en) | 2015-03-25 |
CN104438350B true CN104438350B (en) | 2017-01-18 |
Family
ID=52885543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310436580.4A Active CN104438350B (en) | 2013-09-24 | 2013-09-24 | Strip steel mechanical performance online detection and control method in leveling process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104438350B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106269861B (en) * | 2016-08-26 | 2019-02-01 | 首钢京唐钢铁联合有限责任公司 | Utilize the process of planisher skin-pass rolling galvanized steel |
CN106825069B (en) * | 2017-03-22 | 2018-07-17 | 宁波宝新不锈钢有限公司 | A kind of cold-strip steel high precision plates shape surface roughness on-line intelligence control method |
CN108760873A (en) * | 2018-04-23 | 2018-11-06 | 南京航空航天大学 | Metal material tensile strength quantitative testing device based on incremental permeability and method |
CN109248924A (en) * | 2018-10-26 | 2019-01-22 | 山东钢铁集团日照有限公司 | A kind of cold-strip steel machinery performance online closed loop control method |
CN111378829A (en) * | 2018-12-31 | 2020-07-07 | 瑨祥(宜昌)机电设备有限公司 | Process method for adjusting annealing furnace on line through measurement of elongation of withdrawal and straightening machine |
CN110773580B (en) * | 2019-09-19 | 2021-02-02 | 北京冶自欧博科技发展有限公司 | Method and system for calculating rolling force based on XGboost algorithm |
CN110814050B (en) * | 2019-10-24 | 2021-07-09 | 唐山钢铁集团有限责任公司 | Rolling mill model control method based on BP neural network |
CN114113294B (en) * | 2020-08-28 | 2023-12-12 | 宝山钢铁股份有限公司 | Online measuring device and method for determining yield strength and tensile strength of strip steel |
CN112676376B (en) * | 2020-12-30 | 2021-12-14 | 南通铭泰机床有限公司 | Method and system for improving control precision of numerically controlled plate bending machine |
CN114798764A (en) * | 2022-03-01 | 2022-07-29 | 南京航空航天大学 | Method for measuring yield strength of cold-rolled strip steel on line based on multi-magnetic fusion |
CN114713640A (en) * | 2022-04-12 | 2022-07-08 | 南京钢铁股份有限公司 | Production control method of hot-rolled straight HRB400 steel bar containing Nb component |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102277477A (en) * | 2010-06-09 | 2011-12-14 | 鞍钢股份有限公司 | Establishment method for prediction model of tensile strength of cold rolled strip |
-
2013
- 2013-09-24 CN CN201310436580.4A patent/CN104438350B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102277477A (en) * | 2010-06-09 | 2011-12-14 | 鞍钢股份有限公司 | Establishment method for prediction model of tensile strength of cold rolled strip |
Non-Patent Citations (4)
Title |
---|
双机架平整机延伸率控制系统技术研究;孙明军;《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)》;20121015(第10期);第I140-1203页 * |
基于BP神经网络的冷轧带钢的力学性能预测;侍红岩,等.;《重型机械科技》;CNKI;20060925(第3期);第38-40页 * |
杨喆.平整机延伸率自动控制系统的研究.《中国优秀硕士学位论文全文数据库 信息科技辑(月刊)》.2007,(第01期),第I140-74 页. * |
郑晖.利用人工神经网络预测板带力学性能的软件开发.《塑性工程学报》.CNKI,2003,第10卷(第5期),第71-75页. * |
Also Published As
Publication number | Publication date |
---|---|
CN104438350A (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104438350B (en) | Strip steel mechanical performance online detection and control method in leveling process | |
CN103459646B (en) | The high strength cold rolled steel plate of local deformaton ability excellence and manufacture method thereof | |
CN107377634B (en) | A kind of hot-strip outlet Crown Prediction of Media method | |
CN102886383B (en) | Method for controlling mechanical properties of cold-rolling strip steel in online manner | |
CN102029292B (en) | Strip steel thickness feedforward control method based on mechanical property detection | |
CN110110839B (en) | Strip steel cold rolling lateral thickness difference forecasting method based on PSO-LM-BP neural network | |
CN104942019B (en) | A kind of cold rolling of strip steel process Automatic control method of width | |
JP5003483B2 (en) | Material prediction and material control device for rolling line | |
CN106825069B (en) | A kind of cold-strip steel high precision plates shape surface roughness on-line intelligence control method | |
CN102294364A (en) | Method for presetting rolling force of extremely-thin board temper mill | |
CN103191919B (en) | Optimizing method for on-line control to coefficient model during strip rolling | |
CN104942017B (en) | The determination method of lateral thick difference of cold-rolling strip steels | |
CN107008758A (en) | Cold-strip steel high accuracy plate shape surface roughness On-Line Control Method and system | |
CN111563686A (en) | Cold-rolled silicon steel quality judgment method based on full-process data | |
CN115815345A (en) | Mechanism collaborative prediction method and system for predicting mechanical property of full-flow hot-rolled strip steel | |
Yang et al. | EM sensor array system and performance evaluation for in-line measurement of phase transformation in steel | |
CN108763637B (en) | Calculation and prejudgment method for tensile strength of hot-rolled wire | |
CN107486587B (en) | Thinning compensation method for improving control precision of shearing setting model | |
CN105598186B (en) | A kind of flatness evaluation system and its method based on the horizontal flatness distribution of strip | |
CN105160127B (en) | Performance prediction method based on CSP flow hot continuous rolling production line Q235B steel grades | |
CN114331195A (en) | Process curve risk evaluation method for influencing overall length quality of hot-rolled strip steel | |
CN101748269A (en) | Correlation and integration method for full-flow data of central technological section of continuous annealing production line | |
CN115392104A (en) | Method for predicting mechanical property of cold-rolled continuous annealing strip steel based on annealing process | |
CN104525580B (en) | Cold rolling flat elongation controlling system and method | |
CN107941807B (en) | Quantitative analysis method for center defects of continuous casting slab |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |